What Flows just did
Based on your request to build Single-Agent vs Multi-Agent: Decide and Design, Flows created 4 implementation stages and 12 checks.
You asked for: Make an evidence-based single vs multi decision for my use case, and produce the corresponding architecture sketch.. Flows generated 4 stages because the application requires A written workload analysis: separability, shared-state needs, latency and cost budgets; A scored decision matrix comparing single-loop, sub-agent delegation, and full multi-agent; The chosen architecture sketched with roles, communication paths, and failure handling. Each stage tells your AI builder what to do, tests whether it actually worked, and gives a repair instruction when it fails. These checks are designed to catch: Choosing multi-agent because the demo looked impressive; Underestimating coordination cost: message passing, state sync, partial failures; Role-play theater: five agents doing what one prompt would do better.
Example failure
The form reported success, but no database record was created.
What Flows does
Flows detects the failure, generates a repair instruction, reruns the test, and stores the passing evidence.
Stages — Plan → Build → Test → Fix → Prove → Ship
4 stages · 12 checks · progressive disclosure — open a stage for details
Copy to external builder
Copies a prompt for Claude/Cursor/etc. Records prompt_copied only — not execution, commits, or checks.
Execute through Oort
Requires Sign in with Oort + a provider connection (BYOK). Keys stay on Oort. A model name in the dropdown is not the same as a live connection.
Next
Check off: All five questions answered with specifics
Add a proof note on each check — a checkbox alone is weak proof.
Probes & advanced tools are under “More verification tools”. Experience level: Settings.
Project (saved with proof)
Project binding: Unbound — complete project binding before trusting this run · missing repositoryUrl, repositoryStartCommit, environment, stack
More verification tools (probes, timeline, adapters)Show
App persistence (create → read → assert token)
Body template: {"probe":"{{token}}","title":"flows-probe-{{token}}"}. Needs CORS-readable public create/list endpoints (or inconclusive). Badge only when create→read→refresh finds the token (detects false success).
Two-account authorization (User B cannot see/change User A)
Authorization evidence source: Cross-account ownership test (trust level 5/6). These are not equivalent. Unauthenticated probe alone is weaker (source: unauthenticated API probe). Tokens stay in this browser session only — not uploaded to Flows servers.
Generated edge-case tests (review / approve)
- cross_account_probe User B cannot see or change User A’s data
- cross_account_probe Participant cannot call coach/admin endpoints
- cross_account_probe URL/body ID tampering cannot cross tenant boundary
- api_probe Create then refresh still shows the record
- api_probe Edit then refresh keeps the edit
- api_probe Delete then refresh removes the record
- api_probe Nonexistent record ID fails cleanly
- cross_account_probe Cross-user record identifier is rejected
Generated from this route’s signals — you approve; you do not invent security tests.
Content probe (GET body contains text)
In-product content probe reads response text when CORS allows — not full DOM/click automation. Playwright script is optional and external.
Proof strength
thin · 0/100
Heuristic from notes + probes + gates — not a production certification.
Verification adapters
- ● Deploy URL probe · idle
- ● API path probe · idle
- ● Authz probe (unauth → 401/403) · idle
- ● Browser persistence · idle
- ● App persistence (create→read) · idle
- ● Content / body text probe · idle
- ○ In-product Playwright DOM · not embedded (download external script)
Filled circles = available here. Empty = not shipped. Probes are not a production audit. Adapter docs
Step 1 of 4
Not startedAnalyze the workload for separability
The architecture question is really a workload question.
Flows keeps plan, checks, failures, and next steps connected
Your AI tool writes or changes the code
Repository grounds the plan only after inspect
Checks always carry a validation tier
How this plan was created
Plan from project details
Flows creates steps using the goal, requirements, stack, platform, and details you provide.
- Project description
- Selected template / route
- User-entered stack
- Constraints and notes
- Single-Agent vs Multi-Agent: Decide and Design
No repository inspection implied. Connect and inspect a codebase to ground steps in real files.
Codebase access
Checking GitHub…
Or paste a repository URL manually
Use these instructions in Claude, ChatGPT, Cursor, Emergent, or another builder.
Analyze my agent workload before choosing an architecture. Answer in writing: (1) Can the work be split into subtasks that do NOT need to share intermediate state? (2) Do subtasks need different tool sets or different permission levels? (3) Is there a natural review/producer split where one context should not contaminate the other? (4) What are my latency and cost budgets per task? (5) What is the blast radius if two workers act on stale views of shared state? Produce a one-page workload profile with these answers and concrete examples from my actual use case: [DESCRIBE YOUR USE CASE].
Project context
Copies the project goal, technical details, current step, previous progress, and checks so your AI tool understands what it is working on.
Expected after this step
A one-page workload profile answering the five separability questions.
Should not happen
- ✕Choosing multi-agent because the demo looked impressive
- ✕Underestimating coordination cost: message passing, state sync, partial failures
- ✕Role-play theater: five agents doing what one prompt would do better
- ✕No plan for what happens when one agent in a chain returns garbage
Verify gate — prove this step works before continuing
Do not move on until every check is true. Add proof notes — a checked box alone is weak proof. Checks are manual by default; deploy/API probes live under “More verification tools” and do not auto-check boxes.
Do not continue if…
- !Choosing multi-agent because the demo looked impressive
- !Underestimating coordination cost: message passing, state sync, partial failures
- !Role-play theater: five agents doing what one prompt would do better
- !No plan for what happens when one agent in a chain returns garbage
Repair path — if this step fails
Use the Repair Prompt when a verify gate fails. Loop: Detected → Diagnosed → Repair issued → Changed → Retested → Resolved
Show repair prompt textShow
The analysis is generic. Redo it against three real example tasks from my domain, tracing exactly what state each subtask reads and writes.
Your notes for this step
Definition of Done
Final route-level requirements. Manual checks — separate from per-step verify gates. Completing step gates does not auto-check these. Route completion is not a production-ready claim.